© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119301
    Prev
    Next
    INDEX
    Explanations

    code delimiters // or ">

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flexDirection
    -0.94
    SLT
    -0.85
    паси
    -0.85
    arine
    -0.81
     chilen
    -0.80
    Stre
    -0.78
     disperse
    -0.78
    
    -0.77
    closes
    -0.77
    化した
    -0.76
    POSITIVE LOGITS
     esperienza
    0.85
    Etter
    0.84
     example
    0.84
     tensione
    0.82
     parere
    0.81
     updated
    0.81
     navigazione
    0.81
     pensiero
    0.81
     impactful
    0.79
     toată
    0.79
    Activations Density 0.000%

    No Known Activations